英文词性分类

目前英文词性分类主流方法和工具为：
1.中文普通任务直接用分词工具就够了，jieba、Hanlp、Ansj、Standfordnlp；
2.自己准备语料，HMM、CRF，现在神经网络训练的话一般就是CRF++工具（可以构建特征）、CNN-LSTM（简单些）、Bi-LSTM+CRF（用得最多）、或者是BERT+BiLSTM+CRF（新）。
我自己尝试了Stanfordnlp和spacy，可以使用。

import spacy

nlp = spacy.load('en_core_web_sm')
doc = nlp(u'This is a sentence .')
for token in doc:
    print(token, token.pos_, token.pos)
for nounc in doc.noun_chunks:
    print(nounc)
#with open('demo.txt', mode='r', encoding='UTF-8') as f: 
def getFileContent(path):
    with open(path,'r') as f:
        return f.read()
demo = nlp(getFileContent('./demo.txt'))
#    demo = nlp(’f‘)
for nounc in demo.noun_chunks:
    print(nounc)

or

file = open("demo.txt", "r")
doc = nlp(file.read())
for np in doc.noun_chunks:
    print(np.text)

or

import spacy

nlp = spacy.load("en")

doc = nlp("We try to explicitly describe the geometry of the edges of the images.")

for np in doc.noun_chunks: # use np instead of np.text
    print(np)

print()

# code to recursively combine nouns
# 'We' is actually a pronoun but included in your question
# hence the token.pos_ == "PRON" part in the last if statement
# suggest you extract PRON separately like the noun-chunks above

index = 0
nounIndices = []
for token in doc:
    # print(token.text, token.pos_, token.dep_, token.head.text)
    if token.pos_ == 'NOUN':
        nounIndices.append(index)
    index = index + 1


print(nounIndices)
for idxValue in nounIndices:
    doc = nlp("We try to explicitly describe the geometry of the edges of the images.")
    span = doc[doc[idxValue].left_edge.i : doc[idxValue].right_edge.i+1]
    span.merge()

    for token in doc:
        if token.dep_ == 'dobj' or token.dep_ == 'pobj' or token.pos_ == "PRON":
            print(token.text)

or

from stanfordcorenlp import StanfordCoreNLP
import nltk
from nltk.tree import Tree as nltkTree

nlp = StanfordCoreNLP('./StanfordNLP工具包/stanford-corenlp-full-2018-02-27') 

sentence = 'person removes plate out of cabinet' #输入句子

sen_tag = nlp.pos_tag(sentence)  #词性标注
print(sen_tag)
noun_word = []
for i in range(len(sen_tag)):
    if sen_tag[i][1] == 'NN':
        noun_word.append(sen_tag[i][0])
print(noun_word)

参考文章：
https://blog.csdn.net/lsp1991/article/details/22733619
https://my.oschina.net/u/4232146/blog/4626208
http://www.manongjc.com/article/40737.html
https://spacy.io/models
https://zhuanlan.zhihu.com/p/51425975
https://www.it1352.com/1683784.html
http://www.mamicode.com/info-detail-2686258.html
http://stanfordnlp.github.io/CoreNLP/
https://github.com/stanfordnlp/CoreNLP
https://www.zhihu.com/question/29940957
https://www.jianshu.com/p/931c49830754
https://www.cnblogs.com/maoerbao/p/13019276.html
https://www.it610.com/article/1188489230905614336.htm
https://www.it610.com/article/1188489230905614336.htm
https://zhuanlan.zhihu.com/p/137226095
https://blog.csdn.net/weixin_34613450/article/details/84317158
https://zhuanlan.zhihu.com/p/44180488

本文链接：